CN113204280A - Method, system, equipment and medium for diagnosing power failure - Google Patents
Method, system, equipment and medium for diagnosing power failure Download PDFInfo
- Publication number
- CN113204280A CN113204280A CN202110501950.2A CN202110501950A CN113204280A CN 113204280 A CN113204280 A CN 113204280A CN 202110501950 A CN202110501950 A CN 202110501950A CN 113204280 A CN113204280 A CN 113204280A
- Authority
- CN
- China
- Prior art keywords
- data
- source
- fault
- model
- domain data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
- G06F1/26—Power supply means, e.g. regulation thereof
- G06F1/30—Means for acting in the event of power-supply failure or interruption, e.g. power-supply fluctuations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Abstract
The invention discloses a method, a system, equipment and a storage medium for diagnosing power failure, wherein the method comprises the following steps: acquiring original multi-source data of a power supply in a normal state and a fault state, and preprocessing the original multi-source data to obtain multi-source data; in the off-line stage, depth feature extraction is carried out on the multi-source data to obtain source domain data, and a pre-training model is obtained according to the source domain data; in an online stage, performing depth feature extraction on the multi-source data to respectively obtain source domain data and target domain data, and reducing the distribution difference of the source domain data and the target domain data to update the pre-training model into a training model; and predicting the fault type of the power supply according to the training model. The method adopts domain adaptive transfer learning to intelligently identify the UPS state of the data center, can automatically diagnose the UPS fault type, has high robustness and saves manpower.
Description
Technical Field
The present invention relates to the field of power supplies, and more particularly, to a method, a system, a computer device, and a readable medium for diagnosing a power failure.
Background
With the continuous acceleration of the digitization process and the continuous progress of the artificial intelligence technology, the demand of the data center is more and more increased. The Modular Data Center (MDC) is a new concept adopted to deal with changes of servers such as cloud computing, virtualization, centralization and densification and to improve the operation efficiency of the data center, and has the advantages of rapid deployment, green energy conservation and flexible expansion compared with the conventional data center. The state monitoring and the abnormity early warning of the data center are important components of intelligent operation and maintenance management. With the increasing scale and complexity of data centers, the difficulty of operation and maintenance management thereof is increasing. This is mainly due to the fact that the association and coupling between systems are enhanced, and a problem in one link not only affects the subsystem, but also may cause an abnormality of the associated subsystem. In a data center, an UPS (Uninterruptible Power Supply) is an intermediate device that connects an ac Power Supply and a powered device, and may output stable Power as a backup Power system to protect data security in a data center server. Uncertain factors in the system, such as fluctuation of grid voltage, output overload, change of ambient temperature and the like, can cause problems of overcurrent of the UPS inverter, abnormal rectifier and the like, and the abnormal conditions can cause abnormal power supply of the UPS to further affect safe operation of the data center, so that condition monitoring and fault diagnosis are necessary.
The traditional UPS fault diagnosis method mainly identifies the fault type through a modeling method based on expert knowledge and machine learning. The modeling method based on expert knowledge requires a large number of knowledge rules to be established, and parameters in the judgment rules are set depending on the expert knowledge and have certain randomness, so that the method is difficult to establish an accurate fault diagnosis model. The UPS fault diagnosis based on machine learning obtains key indexes representing the UPS state through feature extraction and feature selection, and on the basis, the UPS state is recognized through a machine learning intelligent recognition model. The method mainly extracts the features manually, has certain subjectivity, and the quality of the selected features has direct influence on the fault diagnosis result.
In recent years, with the continuous progress of deep learning technology, it has been highlighted in the fields of image processing and recognition. However, there is little research in the field of UPS fault diagnosis, and there are the following problems: 1) the UPS failure data of the data center is less serious unbalance compared with normal data; 2) the UPS data of the data center is influenced by factors such as external environment and the like and is in dynamic change, so that the training data is inconsistent with the actual field data. 3) The training data model is difficult to adapt to the distribution of the field data and thus produces poor recognition results.
Therefore, the fault diagnosis by adopting the rule method of expert knowledge has the defects of difficult establishment of a rule base and strong subjectivity in parameter setting; the fault diagnosis by adopting the machine learning modeling method has the defects of complicated manual feature extraction, strong subjectivity and dependence of the fault diagnosis accuracy on the feature selection quality; the traditional deep learning UPS fault diagnosis method has the defects that the adaptability of the different distribution data model is poor, and the fault prediction is accurately influenced by the difference of the data distribution.
Disclosure of Invention
In view of this, an object of the embodiments of the present invention is to provide a method, a system, a computer device, and a computer-readable storage medium for diagnosing a power failure, where the method, the system, the computer device, and the computer-readable storage medium are used to generate an anti-network 1D-WGAN through one-dimensional Wasserstein to augment small sample failure data and increase the number of failure samples; deep feature extraction is carried out on original UPS multi-source data through a variable-scale sliding window method and a DBN network; by adopting an MK-MMD characteristic measurement criterion, the distribution difference between UPS source domain data and target domain data is reduced, model parameters are updated in an online self-adaptive manner, and the updated network model predicts UPS faults in an online manner, so that the defects in the prior art can be effectively overcome.
In view of the above, an aspect of the embodiments of the present invention provides a method for diagnosing a power failure, including the following steps: acquiring original multi-source data of a power supply in a normal state and a fault state, and preprocessing the original multi-source data to obtain multi-source data; in the off-line stage, depth feature extraction is carried out on the multi-source data to obtain source domain data, and a pre-training model is obtained according to the source domain data; in an online stage, performing depth feature extraction on the multi-source data to respectively obtain source domain data and target domain data, and reducing the distribution difference of the source domain data and the target domain data to update the pre-training model into a training model; and predicting the fault type of the power supply according to the training model.
In some embodiments, the pre-processing the raw multi-source data to obtain multi-source data comprises: and augmenting the original multi-source data in the fault state to obtain first multi-source data, and combining the first multi-source data with the original multi-source data in the normal state to obtain the multi-source data.
In some embodiments, the augmenting the raw multi-source data in the fault condition to obtain first multi-source data comprises: constructing a generation model and a discrimination model; inputting noise data in the original multi-source data in the fault state into the generation model to obtain a generation sample, and inputting the generation sample and fault data in the original multi-source data in the fault state into the discrimination model for discrimination; responding to the discrimination model to distinguish fault data and a generated sample, adjusting the generated model according to the difference between the generated sample and the fault data, and returning to the previous step; and responding to the judgment model that the fault data and the generated sample cannot be distinguished, and amplifying the fault data through the generated model.
In some embodiments, the online stage performing depth feature extraction on the multi-source data to obtain source domain data and target domain data, respectively, includes: extracting local features of the multi-source data by adopting a variable-scale sliding window method and an RBM (radial basis function) network; and adopting a DBN network model to fuse the local features so as to extract deep-level features.
In some embodiments, the reducing the difference in the distribution of the source domain data and the target domain data to update the pre-trained model to a trained model comprises: and reducing the distribution difference of the source domain data and the target domain data by adopting an MK-MMD characteristic metric criterion.
In some embodiments, the reducing the distribution difference of the source domain data and the target domain data using an MK-MMD feature metric criterion includes: and performing difference measurement on the source domain features and the target domain features by utilizing the linear combination of the multiple basic kernels.
In some embodiments, the reducing the distribution difference of the source domain data and the target domain data using an MK-MMD feature metric criterion includes: network parameters are updated by back-propagation to reduce the difference between the source domain and the target domain.
In another aspect of the embodiments of the present invention, a system for diagnosing a power failure is provided, including: the system comprises a preprocessing module, a data processing module and a data processing module, wherein the preprocessing module is configured to collect original multi-source data of a power supply in a normal state and a fault state and preprocess the original multi-source data to obtain multi-source data; the creating module is configured to perform depth feature extraction on the multi-source data in an off-line stage to obtain source domain data, and obtain a pre-training model according to the source domain data; the updating module is configured to perform depth feature extraction on the multi-source data at an online stage to respectively obtain source domain data and target domain data, and reduce the distribution difference of the source domain data and the target domain data to update the pre-training model into a training model; and the execution module is configured for predicting the fault type of the power supply according to the training model.
In another aspect of the embodiments of the present invention, there is also provided a computer device, including: at least one processor; and a memory storing computer instructions executable on the processor, the instructions when executed by the processor implementing the steps of the method as above.
In a further aspect of the embodiments of the present invention, a computer-readable storage medium is also provided, in which a computer program for implementing the above method steps is stored when the computer program is executed by a processor.
The invention has the following beneficial technical effects:
(1) the UPS state of the data center is intelligently identified by adopting domain self-adaptive transfer learning, the UPS fault type can be automatically diagnosed, the robustness is high, and the labor is saved;
(2) the UPS state of the data center can be predicted in real time, and the early warning result is fed back to an administrator through a mail or a mobile terminal to achieve intelligent early warning.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other embodiments can be obtained by using the drawings without creative efforts.
FIG. 1 is a schematic diagram of an embodiment of a method of diagnosing a power failure provided by the present invention;
fig. 2 is a schematic diagram of a network structure for generating 1D-WGAN fault data according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a hardware configuration of an embodiment of a computer apparatus for diagnosing a power failure according to the present invention;
FIG. 4 is a schematic diagram of an embodiment of a computer storage medium for diagnosing a power failure provided by the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the following embodiments of the present invention are described in further detail with reference to the accompanying drawings.
It should be noted that all expressions using "first" and "second" in the embodiments of the present invention are used for distinguishing two entities with the same name but different names or different parameters, and it should be noted that "first" and "second" are merely for convenience of description and should not be construed as limitations of the embodiments of the present invention, and they are not described in any more detail in the following embodiments.
In view of the above objects, a first aspect of embodiments of the present invention proposes an embodiment of a method of diagnosing a power failure. Fig. 1 is a schematic diagram illustrating an embodiment of a method for diagnosing a power failure according to the present invention. As shown in fig. 1, the embodiment of the present invention includes the following steps:
s1, collecting original multi-source data of a power supply in a normal state and a fault state, and preprocessing the original multi-source data to obtain multi-source data;
s2, performing depth feature extraction on the multi-source data in an off-line stage to obtain source domain data, and obtaining a pre-training model according to the source domain data;
s3, performing depth feature extraction on the multi-source data at an online stage to respectively obtain source domain data and target domain data, and reducing the distribution difference of the source domain data and the target domain data to update the pre-training model into a training model; and
and S4, predicting the fault type of the power supply according to the training model.
Aiming at the defects of the prior art, the invention provides a data center UPS fault diagnosis method based on domain self-adaptive transfer learning and small sample data. According to the method, a countermeasure network 1D-WGAN is generated through one-dimensional Wasserstein to amplify small sample fault data and increase the number of fault samples; deep feature extraction is carried out on original UPS multi-source data through a variable-scale sliding window method and a DBN network; and reducing the distribution difference between the UPS source domain data and the target domain data by adopting an MK-MMD characteristic measurement criterion, updating model parameters in an online self-adaptive manner, and predicting the UPS faults by the updated network model online.
The method comprises the steps of collecting original multi-source data of a power supply in a normal state and a fault state, and preprocessing the original multi-source data to obtain multi-source data.
In some embodiments, the pre-processing the raw multi-source data to obtain multi-source data comprises: and augmenting the original multi-source data in the fault state to obtain first multi-source data, and combining the first multi-source data with the original multi-source data in the normal state to obtain the multi-source data.
In order to select data representing UPS faults, the invention integrates UPS multi-source data to extract fault characteristics, and the selected data is shown in the following table:
| serial number | Data of | Name (R) | |
| 1 | Input current A | Input_Current_A | |
| 2 | Input | Input_Current_B | |
| 3 | Input current C | Input_Current_C | |
| 4 | Output current A | Output_Current_A | |
| 5 | Output voltage A | Output_Voltage_A | |
| 6 | Output load | Output_Workload | |
| 7 | UPS temperature | UPS_Temperature | |
| 8 | Ambient temperature | ENV_Temperatutre | |
| 9 | Humidity of the environment | ENV_Humidity |
In practical application, the UPS fault data generated on site is less and has larger difference with normal sample data, and in order to increase the number of fault samples, the invention provides a 1D-WGAN network model to expand the fault data.
In some embodiments, the augmenting the raw multi-source data in the fault condition to obtain first multi-source data comprises: constructing a generation model and a discrimination model; inputting noise data in the original multi-source data in the fault state into the generation model to obtain a generation sample, and inputting the generation sample and fault data in the original multi-source data in the fault state into the discrimination model for discrimination; responding to the discrimination model to distinguish fault data and a generated sample, adjusting the generated model according to the difference between the generated sample and the fault data, and returning to the previous step; and responding to the judgment model that the fault data and the generated sample cannot be distinguished, and amplifying the fault data through the generated model. The generative model comprises an input layer, a one-dimensional convolutional layer, a fully connected layer and an output layer. The UPS noise data of the input layer and the UPS fault data generated by the output layer are recorded as Xi'＝(xi1',xi2',xi3',...xi9'), i ═ 1, 2. Where i is the number of samples. The discriminant model comprises an input layer, a one-dimensional convolutional layer, a Maxpooling1D layer, a Flatten layer, a Dropout layer, a full-link layer and an output layer. Wherein, the input layer is a real UPS fault Xi＝(xi1,xi2,xi3,...xi9) N and generated UPS fault data Xi. Outputting as true fault numberBased on or to generate a prediction of fault data.
The Wasserstein distance metric function adopted by WGAN measures between real data and generated data distribution, and the loss function is as follows: the generator loss function:
the discriminator loss function is:
the loss function is such that when the generator is fixed, the distribution distance between the real fault samples and the generated fault samples is increased as much as possible, the loss function LcApproximating the Wasserstein distance between the two. When the discriminator is fixed, the distribution distance between the generated fault sample and the real fault sample is reduced as much as possible, the loss function LgApproximating the Wasserstein distance between the two.
The overall network structure for fault data generation is shown in fig. 2. As shown in fig. 2, the multi-source data is divided into UPS fault data and UPS noise data, the UPS fault data is directly input as a real sample to a discriminant model, the UPS noise data forms a generated sample input discriminant model through a generative model, and if the discriminant model can identify the real sample and the generated sample, it indicates that the generative model is not perfect and further adjustment is required. The generative model may be further adjusted based on the output of the discriminant model. Until the discrimination model fails to identify the true samples and the generated samples, the generated model may be used to augment the UPS fault data.
And in the off-line stage, depth feature extraction is carried out on the multi-source data to obtain source domain data, and a pre-training model is obtained according to the source domain data.
And in an online stage, performing depth feature extraction on the multi-source data to respectively obtain source domain data and target domain data, and reducing the distribution difference of the source domain data and the target domain data to update the pre-training model into a training model.
In some embodiments, the online stage performing depth feature extraction on the multi-source data to obtain source domain data and target domain data, respectively, includes: extracting local features of the multi-source data by adopting a variable-scale sliding window method and an RBM (radial basis function) network; and adopting a DBN network model to fuse the local features so as to extract deep-level features.
The traditional DBN network fault identification method preprocesses original data and manually extracts features to input the features into a network model to judge fault types, but the method cannot fully utilize the information of the original data, and therefore, the invention adopts a sliding window method to combine an RBM network to extract local features. Noting that the length of a single sample datum is L, the length of a sliding window unit is L, the sliding step length is T, and then the number of visible layer nodes in the RBM network is as follows:
extracting the characteristics of the original data by a sliding window method and an RBM network to obtain:
f is to beRBMInputting the features into a DBN network for deep feature extraction to obtain:
due to the fact that the data distribution is different due to the fact that working condition difference exists between the test data and the training data, MK-MMD is adopted for FDBNThe features are subjected to domain adaptive learning to reduce the difference between the two data distributions. And online updating network parameters to identify the UPS faults.
In some embodiments, the reducing the difference in the distribution of the source domain data and the target domain data to update the pre-trained model to a trained model comprises: and reducing the distribution difference of the source domain data and the target domain data by adopting an MK-MMD characteristic metric criterion.
In some embodiments, the reducing the distribution difference of the source domain data and the target domain data using an MK-MMD feature metric criterion includes: and performing difference measurement on the source domain features and the target domain features by utilizing the linear combination of the multiple basic kernels.
In some embodiments, the reducing the distribution difference of the source domain data and the target domain data using an MK-MMD feature metric criterion includes: network parameters are updated by back-propagation to reduce the difference between the source domain and the target domain.
In order to reduce the difference in data distribution between the test data and the training data, the invention performs adaptive migration learning on the source domain data and the target domain data from the feature layer. The specific method comprises the following steps:
(1) extracting local features of UPS multi-source data by adopting a variable-scale sliding window method and an RBM network;
(2) fusing the local features by adopting a DBN network model to extract deep-level features;
(3) reducing the difference of the characteristic domains and updating the model parameters by adopting an MK-MMD characteristic measurement criterion;
(4) and the updated network parameters are used for online reasoning and fault identification of the test data.
Wherein the MK-MMD characteristic metric function is as follows:
wherein φ (-) represents the mapping k (x) to the kernels,xt)＝<φ(xs),φ(xt)>And (4) relevant feature mapping. k (x)s,xt) Expressed as a linear combination of l basic kernels:
and performing difference measurement on the source domain features and the target domain features by utilizing linear combination of the basic kernels, incorporating the distance measurement parameters into a loss function, and reducing the difference between the source domain and the target domain by updating network parameters through back propagation.
And predicting the fault type of the power supply according to the training model.
In order to more clearly illustrate the technical solution of the present invention, the steps of the present invention will now be described by way of example:
(1) collecting multi-source data of the UPS in three states of normal, bypass fault and hardware fault;
(2) the 1D-WGAN is adopted to amplify the small sample fault data so as to improve the number of UPS fault samples;
(3) local feature extraction is carried out on UPS multi-source data by using offline data and adopting a variable-scale sliding window method and an RBM network;
(4) fusing local features by using offline data and adopting a DBN (database-based network) model to extract deep features;
(5) training the network model by using the offline data to obtain a pre-training model;
(6) inputting online data and offline data into a pre-training model, and executing a variable-scale sliding window method and an RBM network to perform local feature extraction on UPS multi-source data;
(7) inputting local characteristics of online data and offline data into a DBN network to output deep-level characteristics;
(8) performing distance measurement on the deep-level features of the online data and the offline data by adopting MK-MMD, calculating the overall loss, updating through back propagation network parameters, and outputting the UPS state by the updated network model;
(9) and finishing the web end deployment and the check of the UPS state real-time prediction result by adopting a flash.
The following table shows the accuracy of UPS fault diagnosis in the training state and the testing state for different methods:
| Method | training accuracy | Accuracy of test |
| DBN | 93％ | 62％ |
| LRBM+DBN | 94％ | 74％ |
| LRBM+DBN+1D-WGAN | 92％ | 78％ |
| LRBM + DBN +1D-WGAN + MK-MMD (invention) | 98％ | 91％ |
Wherein, the DBN is a traditional method for extracting artificial features and then adopts a DBN identification method; LRBM adopts RBM local feature extraction and matches with DBN identification method; LRBM + DBN +1D-WGAN extracts RBM local features after fault samples are amplified and is matched with a DBN identification method; the results of the UPS fault diagnosis provided by the invention are LRBM + DBN +1D-WGAN + MK-MMD, and the results show that the performance of the UPS fault diagnosis system is optimal in both training data and field verification data.
The invention provides a data center UPS fault diagnosis method based on domain self-adaptive transfer learning and small sample data. The method expands the small sample fault data by generating the countermeasure network 1D-WGAN to increase the number of fault samples; deep feature extraction is carried out on original UPS multi-source data through a variable-scale sliding window method and a DBN network; and reducing the distribution difference between the UPS source domain data and the target domain data by adopting an MK-MMD characteristic measurement criterion, updating model parameters in an online self-adaptive manner, and predicting the UPS faults by the updated network model online.
It should be particularly noted that, the steps in the embodiments of the method for diagnosing power failure described above can be mutually intersected, replaced, added, or deleted, so that these reasonable permutations and combinations are also intended to fall within the scope of the present invention, and should not limit the scope of the present invention to the embodiments.
In view of the above object, according to a second aspect of the embodiments of the present invention, there is provided a system for diagnosing a power failure, including: the system comprises a preprocessing module, a data processing module and a data processing module, wherein the preprocessing module is configured to collect original multi-source data of a power supply in a normal state and a fault state and preprocess the original multi-source data to obtain multi-source data; the creating module is configured to perform depth feature extraction on the multi-source data in an off-line stage to obtain source domain data, and obtain a pre-training model according to the source domain data; the updating module is configured to perform depth feature extraction on the multi-source data at an online stage to respectively obtain source domain data and target domain data, and reduce the distribution difference of the source domain data and the target domain data to update the pre-training model into a training model; and the execution module is configured for predicting the fault type of the power supply according to the training model.
In some embodiments, the pre-processing module is configured to: and augmenting the original multi-source data in the fault state to obtain first multi-source data, and combining the first multi-source data with the original multi-source data in the normal state to obtain the multi-source data.
In some embodiments, the pre-processing module is configured to: constructing a generation model and a discrimination model; inputting noise data in the original multi-source data in the fault state into the generation model to obtain a generation sample, and inputting the generation sample and fault data in the original multi-source data in the fault state into the discrimination model for discrimination; responding to the discrimination model to distinguish fault data and a generated sample, adjusting the generated model according to the difference between the generated sample and the fault data, and returning to the previous step; and responding to the judgment model that the fault data and the generated sample cannot be distinguished, and amplifying the fault data through the generated model.
In some embodiments, the update module is configured to: extracting local features of the multi-source data by adopting a variable-scale sliding window method and an RBM (radial basis function) network; and adopting a DBN network model to fuse the local features so as to extract deep-level features.
In some embodiments, the update module is configured to: and reducing the distribution difference of the source domain data and the target domain data by adopting an MK-MMD characteristic metric criterion.
In some embodiments, the update module is configured to: and performing difference measurement on the source domain features and the target domain features by utilizing the linear combination of the multiple basic kernels.
In some embodiments, the update module is configured to: network parameters are updated by back-propagation to reduce the difference between the source domain and the target domain.
In view of the above object, a third aspect of the embodiments of the present invention provides a computer device, including: at least one processor; and a memory storing computer instructions executable on the processor, the instructions being executable by the processor to perform the steps of: s1, collecting original multi-source data of a power supply in a normal state and a fault state, and preprocessing the original multi-source data to obtain multi-source data; s2, performing depth feature extraction on the multi-source data in an off-line stage to obtain source domain data, and obtaining a pre-training model according to the source domain data; s3, performing depth feature extraction on the multi-source data at an online stage to respectively obtain source domain data and target domain data, and reducing the distribution difference of the source domain data and the target domain data to update the pre-training model into a training model; and S4, predicting the fault type of the power supply according to the training model.
In some embodiments, the pre-processing the raw multi-source data to obtain multi-source data comprises: and augmenting the original multi-source data in the fault state to obtain first multi-source data, and combining the first multi-source data with the original multi-source data in the normal state to obtain the multi-source data.
In some embodiments, the augmenting the raw multi-source data in the fault condition to obtain first multi-source data comprises: constructing a generation model and a discrimination model; inputting noise data in the original multi-source data in the fault state into the generation model to obtain a generation sample, and inputting the generation sample and fault data in the original multi-source data in the fault state into the discrimination model for discrimination; responding to the discrimination model to distinguish fault data and a generated sample, adjusting the generated model according to the difference between the generated sample and the fault data, and returning to the previous step; and responding to the judgment model that the fault data and the generated sample cannot be distinguished, and amplifying the fault data through the generated model.
In some embodiments, the online stage performing depth feature extraction on the multi-source data to obtain source domain data and target domain data, respectively, includes: extracting local features of the multi-source data by adopting a variable-scale sliding window method and an RBM (radial basis function) network; and adopting a DBN network model to fuse the local features so as to extract deep-level features.
In some embodiments, the reducing the difference in the distribution of the source domain data and the target domain data to update the pre-trained model to a trained model comprises: and reducing the distribution difference of the source domain data and the target domain data by adopting an MK-MMD characteristic metric criterion.
In some embodiments, the reducing the distribution difference of the source domain data and the target domain data using an MK-MMD feature metric criterion includes: and performing difference measurement on the source domain features and the target domain features by utilizing the linear combination of the multiple basic kernels.
In some embodiments, the reducing the distribution difference of the source domain data and the target domain data using an MK-MMD feature metric criterion includes: network parameters are updated by back-propagation to reduce the difference between the source domain and the target domain.
Fig. 3 is a schematic hardware structure diagram of an embodiment of the computer device for diagnosing a power failure according to the present invention.
Taking the apparatus shown in fig. 3 as an example, the apparatus includes a processor 201 and a memory 202, and may further include: an input device 203 and an output device 204.
The processor 201, the memory 202, the input device 203 and the output device 204 may be connected by a bus or other means, and fig. 3 illustrates the connection by a bus as an example.
The memory 202, which is a non-volatile computer-readable storage medium, may be used for storing non-volatile software programs, non-volatile computer-executable programs, and modules, such as program instructions/modules corresponding to the method for diagnosing a power failure in the embodiments of the present application. The processor 201 executes various functional applications of the server and data processing by running the nonvolatile software programs, instructions and modules stored in the memory 202, that is, implements the method of diagnosing power failure of the above-described method embodiment.
The memory 202 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the method of diagnosing a power failure, and the like. Further, the memory 202 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, memory 202 may optionally include memory located remotely from processor 201, which may be connected to local modules via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 203 may receive information such as a user name and a password that are input. The output device 204 may include a display device such as a display screen.
Program instructions/modules corresponding to one or more methods of diagnosing a power failure are stored in the memory 202, and when executed by the processor 201, perform the method of diagnosing a power failure in any of the method embodiments described above.
Any embodiment of a computer apparatus for performing the method for diagnosing a power failure as described above may achieve the same or similar effects as any of the preceding method embodiments corresponding thereto.
The invention also provides a computer readable storage medium storing a computer program which, when executed by a processor, performs the method as above.
Fig. 4 is a schematic diagram of an embodiment of a computer storage medium for diagnosing a power failure according to the present invention. Taking the computer storage medium as shown in fig. 4 as an example, the computer readable storage medium 3 stores a computer program 31 which, when executed by a processor, performs the above method.
Finally, it should be noted that, as one of ordinary skill in the art can appreciate that all or part of the processes of the methods of the above embodiments can be implemented by a computer program to instruct related hardware, and the program of the method for diagnosing a power failure can be stored in a computer readable storage medium, and when executed, can include the processes of the embodiments of the methods as described above. The storage medium of the program may be a magnetic disk, an optical disk, a Read Only Memory (ROM), a Random Access Memory (RAM), or the like. The embodiments of the computer program may achieve the same or similar effects as any of the above-described method embodiments.
The foregoing is an exemplary embodiment of the present disclosure, but it should be noted that various changes and modifications could be made herein without departing from the scope of the present disclosure as defined by the appended claims. The functions, steps and/or actions of the method claims in accordance with the disclosed embodiments described herein need not be performed in any particular order. Furthermore, although elements of the disclosed embodiments of the invention may be described or claimed in the singular, the plural is contemplated unless limitation to the singular is explicitly stated.
It should be understood that, as used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly supports the exception. It should also be understood that "and/or" as used herein is meant to include any and all possible combinations of one or more of the associated listed items.
The numbers of the embodiments disclosed in the embodiments of the present invention are merely for description, and do not represent the merits of the embodiments.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
Those of ordinary skill in the art will understand that: the discussion of any embodiment above is meant to be exemplary only, and is not intended to intimate that the scope of the disclosure, including the claims, of embodiments of the invention is limited to these examples; within the idea of an embodiment of the invention, also technical features in the above embodiment or in different embodiments may be combined and there are many other variations of the different aspects of the embodiments of the invention as described above, which are not provided in detail for the sake of brevity. Therefore, any omissions, modifications, substitutions, improvements, and the like that may be made without departing from the spirit and principles of the embodiments of the present invention are intended to be included within the scope of the embodiments of the present invention.
Claims (10)
1. A method of diagnosing a power failure, comprising the steps of:
acquiring original multi-source data of a power supply in a normal state and a fault state, and preprocessing the original multi-source data to obtain multi-source data;
in the off-line stage, depth feature extraction is carried out on the multi-source data to obtain source domain data, and a pre-training model is obtained according to the source domain data;
in an online stage, performing depth feature extraction on the multi-source data to respectively obtain source domain data and target domain data, and reducing the distribution difference of the source domain data and the target domain data to update the pre-training model into a training model; and
and predicting the fault type of the power supply according to the training model.
2. The method of claim 1, wherein pre-processing the raw multi-source data to obtain multi-source data comprises:
and augmenting the original multi-source data in the fault state to obtain first multi-source data, and combining the first multi-source data with the original multi-source data in the normal state to obtain the multi-source data.
3. The method of claim 2, wherein the augmenting the raw multi-source data in the fault condition to obtain first multi-source data comprises:
constructing a generation model and a discrimination model;
inputting noise data in the original multi-source data in the fault state into the generation model to obtain a generation sample, and inputting the generation sample and fault data in the original multi-source data in the fault state into the discrimination model for discrimination;
responding to the discrimination model to distinguish fault data and a generated sample, adjusting the generated model according to the difference between the generated sample and the fault data, and returning to the previous step; and
and responding to the condition that the discrimination model cannot distinguish fault data and a generated sample, and amplifying the fault data through the generated model.
4. The method of claim 1, wherein the online stage performing depth feature extraction on the multi-source data to obtain source domain data and target domain data, respectively, comprises:
extracting local features of the multi-source data by adopting a variable-scale sliding window method and an RBM (radial basis function) network; and
and fusing the local features by adopting a DBN network model to extract deep-level features.
5. The method of claim 1, wherein the reducing the difference in the distribution of the source domain data and the target domain data to update the pre-trained model to a trained model comprises:
and reducing the distribution difference of the source domain data and the target domain data by adopting an MK-MMD characteristic metric criterion.
6. The method of claim 5, wherein the employing an MK-MMD feature metric criterion to reduce the difference in distribution of the source domain data and the target domain data comprises:
and performing difference measurement on the source domain features and the target domain features by utilizing the linear combination of the multiple basic kernels.
7. The method of claim 6, wherein the employing an MK-MMD feature metric criterion to reduce the difference in distribution of the source domain data and the target domain data comprises:
network parameters are updated by back-propagation to reduce the difference between the source domain and the target domain.
8. A system for diagnosing a power failure, comprising:
the system comprises a preprocessing module, a data processing module and a data processing module, wherein the preprocessing module is configured to collect original multi-source data of a power supply in a normal state and a fault state and preprocess the original multi-source data to obtain multi-source data;
the creating module is configured to perform depth feature extraction on the multi-source data in an off-line stage to obtain source domain data, and obtain a pre-training model according to the source domain data;
the updating module is configured to perform depth feature extraction on the multi-source data at an online stage to respectively obtain source domain data and target domain data, and reduce the distribution difference of the source domain data and the target domain data to update the pre-training model into a training model; and
and the execution module is configured for predicting the fault type of the power supply according to the training model.
9. A computer device, comprising:
at least one processor; and
a memory storing computer instructions executable on the processor, the instructions when executed by the processor implementing the steps of the method of any one of claims 1 to 7.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110501950.2A CN113204280B (en) | 2021-05-08 | 2021-05-08 | Method, system, equipment and medium for diagnosing power failure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110501950.2A CN113204280B (en) | 2021-05-08 | 2021-05-08 | Method, system, equipment and medium for diagnosing power failure |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113204280A true CN113204280A (en) | 2021-08-03 |
| CN113204280B CN113204280B (en) | 2023-09-26 |
Family
ID=77030710
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110501950.2A Active CN113204280B (en) | 2021-05-08 | 2021-05-08 | Method, system, equipment and medium for diagnosing power failure |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113204280B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114660500A (en) * | 2022-05-19 | 2022-06-24 | 秦皇岛广控科技有限公司 | Three-phase monitoring protection system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109947086A (en) * | 2019-04-11 | 2019-06-28 | 清华大学 | Mechanical breakdown migration diagnostic method and system based on confrontation study |
| CN111523785A (en) * | 2020-04-16 | 2020-08-11 | 三峡大学 | Power system dynamic security assessment method based on generation countermeasure network |
| CN111898095A (en) * | 2020-07-10 | 2020-11-06 | 佛山科学技术学院 | Deep migration learning intelligent fault diagnosis method and device, storage medium and equipment |
| CN111898634A (en) * | 2020-06-22 | 2020-11-06 | 西安交通大学 | Intelligent fault diagnosis method based on depth-to-reactance-domain self-adaption |
| CN112101085A (en) * | 2020-07-22 | 2020-12-18 | 西安交通大学 | Adaptive intelligent fault diagnosis method based on importance weighted domain impedance |
| CN112328588A (en) * | 2020-11-27 | 2021-02-05 | 哈尔滨工程大学 | Industrial fault diagnosis unbalanced time sequence data expansion method |
-
2021
- 2021-05-08 CN CN202110501950.2A patent/CN113204280B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109947086A (en) * | 2019-04-11 | 2019-06-28 | 清华大学 | Mechanical breakdown migration diagnostic method and system based on confrontation study |
| CN111523785A (en) * | 2020-04-16 | 2020-08-11 | 三峡大学 | Power system dynamic security assessment method based on generation countermeasure network |
| CN111898634A (en) * | 2020-06-22 | 2020-11-06 | 西安交通大学 | Intelligent fault diagnosis method based on depth-to-reactance-domain self-adaption |
| CN111898095A (en) * | 2020-07-10 | 2020-11-06 | 佛山科学技术学院 | Deep migration learning intelligent fault diagnosis method and device, storage medium and equipment |
| CN112101085A (en) * | 2020-07-22 | 2020-12-18 | 西安交通大学 | Adaptive intelligent fault diagnosis method based on importance weighted domain impedance |
| CN112328588A (en) * | 2020-11-27 | 2021-02-05 | 哈尔滨工程大学 | Industrial fault diagnosis unbalanced time sequence data expansion method |
Non-Patent Citations (2)
| Title |
|---|
| 杨毅 等: "基于深度-迁移学习的输电线路故障选相模型及其可迁移性研究", 《电力自动化设备》 * |
| 杨毅 等: "基于深度-迁移学习的输电线路故障选相模型及其可迁移性研究", 《电力自动化设备》, vol. 40, no. 10, 31 October 2020 (2020-10-31), pages 165 - 171 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114660500A (en) * | 2022-05-19 | 2022-06-24 | 秦皇岛广控科技有限公司 | Three-phase monitoring protection system |
| CN114660500B (en) * | 2022-05-19 | 2022-08-19 | 秦皇岛广控科技有限公司 | Three-phase monitoring protection system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113204280B (en) | 2023-09-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zaher et al. | Online wind turbine fault detection through automated SCADA data analysis | |
| CN116256602B (en) | Method and system for identifying state abnormality of low-voltage power distribution network | |
| CN110988563B (en) | UPS (uninterrupted Power supply) fault detection method, device, equipment and storage medium | |
| CN111524118B (en) | Running state detection method and device of transformer, computer equipment and storage medium | |
| US11656589B2 (en) | Systems and methods for automatic power topology discovery | |
| Kenyon et al. | An agent-based implementation of hidden Markov models for gas turbine condition monitoring | |
| Toshkova et al. | Automatic alarm setup using extreme value theory | |
| CN111881159A (en) | Fault detection method and device based on cost-sensitive extreme random forest | |
| CN113204280B (en) | Method, system, equipment and medium for diagnosing power failure | |
| CN117289085A (en) | Multi-line fault analysis and diagnosis method and system | |
| Pournabi et al. | Power system transient security assessment based on deep learning considering partial observability | |
| US20220360084A1 (en) | Transient stability assessment method for an electric power system | |
| Lutska et al. | Forecasting the efficiency of the control system of the technological object on the basis of neural networks | |
| CN115878992A (en) | Monitoring method and monitoring system for comprehensive pipe rack power supply system | |
| CN117474357A (en) | Power distribution room operation and maintenance management method and system based on deep learning | |
| Hassani et al. | Design of a cost-effective deep convolutional neural network–based scheme for diagnosing faults in smart grids | |
| CN117331790A (en) | Machine room fault detection method and device for data center | |
| CN109889258B (en) | Optical network fault checking method and equipment | |
| Rizvi et al. | Real-time ZIP load parameter tracking using adaptive window and variable elimination with realistic synthetic synchrophasor data | |
| JP2002169611A (en) | Fault diagnosis system and automated design system therefor | |
| CN114662989A (en) | Transient stability self-adaptive evaluation method and device for power system | |
| Gao et al. | Fault detection of electric vehicle charging piles based on extreme learning machine algorithm | |
| CN115598459A (en) | Power failure prediction method for 10kV feeder line fault of power distribution network | |
| Al-Gubri et al. | Performance analysis of machine learning algorithms for power system dynamic security assessment | |
| Wang et al. | Adversarial Based Unsupervised Domain Adaptation for Bearing Fault Diagnosis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |